抽象的

Automatically Extract the Left and Right Ventricular Myocardium from CT Images by Using Region Based Segmentation

Jackulin DuraiRani.A, Yamini.C, Sivaranjani.B, Rekha.A, Jothi.S

Seeded Region Growing is the more gorgeous method in medical image segmentation by using high level information of images for selecting seeds for segmentation. This SRG algorithm that provides the most efficient for fixing the labels for pixels and also for segmentation. This paper represents the automatic system for segmenting the left and right ventricular myocardium CT images by using Region growing method. This algorithm follows the focus on fixing the labels for region growing segmentation. This algorithm that gives the most accurate segmentation of Myocardium from CT images the delineation of the myocardial wall which is a exacting task due to large differences in myocardial shapes and quality of an image. In this paper, we describe an automatic method for extracting the myocardium from the left and right ventricles from CT images. In the method, the left and right ventricles are detected, by first identifying the endocardium and epicardium and then segmenting the myocardium. After that, a seed regiongrowing method is applied to extract the epicardium of the ventricles. In particular, the location of the endocardium of the left ventricle is determined via using an active contour model on the blood-pool surface. To localize the right ventricle, the active contour model is applied on a heart surface extracted based on the left ventricle segmentation result, which gives the high accuracy